Saved toolsSubmit a tool
FOXAI SEARCH

Search FoxAI

AI Models 2119

  • MiniCPM-V-4.7-35B-A3B-int4↗

    openbmb

    > **This repository hosts the int4 (W4A16, compressed-tensors, llm-compressor) quantized version of MiniCPM-V 4.7 35B-A3B.** For the original BF16 weights and the full model card, please refer to openbmb/MiniCPM-V-4.7-35B-A3B. **MiniCPM-V 4.7** is the latest model in the MiniCPM-V series, available in a **35B-A3B** variant, with **35B-A3B being the first MoE model in the MiniCPM-V series**. It builds on the family's single-image, multi-image, and video understanding capabilities, combining stronger foundation capabilities with efficient visual encoding and on-device inference. Notable features of MiniCPM-V 4.7 include: - 📱 **The First Open-Source MoE Model with Lossless, Smooth On-Device Inference.** With our **Lookahead Expert Scheduling (LES)** technique introduced alongside MiniCPM-V 4.7, combined with fine-grained layer-wise quantization and DSpark speculative sampling integration, MiniCPM-V 4.7 35B-A3B becomes the **first open-source MoE model to run smoothly on-device without compromising performance**, achieving a decoding speed of **13+ tokens/s with just 3 GB of memory on iPhone 17 Pro Max**. - 🔥 **A New Pareto Frontier in Performance and Efficiency.** As model capabilities continue to advance, inference efficiency has become an important measure of a model's value. On resource-constrained devices, delivering the strongest possible capabilities within a limited resource budget calls for higher capability density. The **35B-A3B** variant of MiniCPM-V 4.7 advances the performance–efficiency Pareto frontier for MLLMs. In Instruct mode, 35B-A3B **achieves a higher overall score in less inference time than Qwen3.6 35B-A3B**. - 🚀 **Efficient Architecture.** Based on the intra-ViT early compression technique from LLaVA-UHD v4, MiniCPM-V 4.7 compresses visual tokens early within the vision encoder, reducing computation in subsequent encoder layers. It also supports **mixed 4x/16x visual token compression**, allowing developers to balance visual detail and inference cost across tasks. - 💻 **Broad Platform and Chip Support.** MiniCPM-V 4.7 supports **iOS, Android, and HarmonyOS**, together with open-source on-device deployment support. It also provides **day-0 support for chip platforms from Rockchip, Houmo, Intel, AMD, and Arm**, extending deployment options across mobile and local computing devices. - 🛠️ **Developer Friendly.** MiniCPM-V 4.7 supports i

  • FastSam-X↗

    qualcomm

  • pythia-410m↗

    EleutherAI

    The *Pythia Scaling Suite* is a collection of models developed to facilitate interpretability research (see paper). It contains two sets of eight models of sizes 70M, 160M, 410M, 1B, 1.4B, 2.8B, 6.9B, and 12B. For each size, there are two models: one trained on the Pile, and one trained on the Pile after the dataset has been globally deduplicated. All 8 model sizes are trained on the exact same data, in the exact same order. We also provide 154 intermediate checkpoints per model, hosted on Hugging Face as branches. The Pythia model suite was deliberately designed to promote scientific research on large language models, especially interpretability research. Despite not centering downstream performance as a design goal, we find the models match or exceed the performance of similar and same-sized models, such as those in the OPT and GPT-Neo suites. Previously, we released an early version of the Pythia suite to the public. However, we decided to retrain the model suite to address a few hyperparameter discrepancies. This model card lists the changes ; see appendix B in the Pythia paper for further discussion. We found no difference in benchmark performance between the two Pythia versions. The old models are still available, but we suggest the retrained suite if you are just starting to use Pythia. **This is the current release.**

  • GLM-5.3 (Max)↗

    Z AI

    GLM-5.3 uses the same base model as GLM-5.2 — every gain comes from post-training. Compared with GLM-5.2, it is much better at complex coding and long-horizon tasks: + Stronger Coding: GLM-5.3 is the most capable open-weights model for coding, with a 50% improvement over GLM-5.2 on our in-house Z.ai Code Bench. It also achieve open-source SOTA on public benchmarks including Terminal Bench 3.0 and Agents' Last Exam. + Emergent Cyber Capability: As we scaled post-training, cyber capability developed faster than we expected. GLM-5.3 is state of the art on CyberGym for vulnerability discovery, and its gains are largest further up the exploitation chain, where it more than doubles GLM-5.2 on exploitation benchmarks. GLM-5.3 supports deployment with the following frameworks. Feel free to try them out:

  • chronos-t5-mini↗

    amazon

    🚀 **Update Feb 14, 2025**: Chronos-Bolt & original Chronos models are now available on Amazon SageMaker JumpStart! Check out the tutorial notebook to learn how to deploy Chronos endpoints for production use in a few lines of code. 🚀 **Update Nov 27, 2024**: We have released Chronos-Bolt⚡️ models that are more accurate (5% lower error), up to 250 times faster and 20 times more memory-efficient than the original Chronos models of the same size. Check out the new models here. Chronos is a family of **pretrained time series forecasting models** based on language model architectures. A time series is transformed into a sequence of tokens via scaling and quantization, and a language model is trained on these tokens using the cross-entropy loss. Once trained, probabilistic forecasts are obtained by sampling multiple future trajectories given the historical context. Chronos models have been trained on a large corpus of publicly available time series data, as well as synthetic data generated using Gaussian processes.

  • LFM2.5-2.6B-GGUF↗

    Arki05

    17 GGUF files of LiquidAI/LFM2.5-2.6B at the sizes of bartowski's quants and LiquidAI's own, with 26–77 % less KL divergence than the published file of the same size (about half or less from 3 to 5 bits per weight). Two things make the difference: **Build your own size:** the qalloc app solves the mix for any size you pick and assembles the GGUF in your browser, tensor by tensor from the store. Per token, against the BF16 model: the mean KL divergence and its 99th percentile (lower is better), and how often the most likely next token is the BF16 model's (higher is better), for the published file of the same size → this file. Where two published files are within 1 % of each other's size, one file here serves both.

  • gemma-4-12B-it-oQ8e-mtp↗

    Jundot

    This model was quantized using oQ (oMLX v0.7.1) mixed-precision quantization with Improved oQe Quantization (jundot/omlx#4385). A mixed-precision MLX checkpoint of google/gemma-4-12B-it, the 11.95B Unified model of the Gemma 4 family from Google DeepMind. It has no separate encoders: image patches and audio waveforms are projected directly into the embedding space through lightweight linear layers, and all modalities run through a single decoder-only transformer with a 256K-token context. It includes the model and a multi-token prediction (MTP) head merged from google/gemma-4-12B-it-assistant. oQ8e allocates bits by measured layer sensitivity, then rounds each group with an importance matrix (128 samples x 512 tokens) and a weighted least-squares refit of its scale and bias.

  • grug-27b-qat-q4-gguf↗

    ProCreations

    **2026-07-23 refresh: rock now QAT-trained from grug-27b v2.1 weights** (deep-think + agent-discipline update). bench table below measured on the v1-era rock vs v1 control - directional guide still; v2.1 rock inherit both the QAT recovery AND the v2.1 brain improvements. grug put 27b brain in four-bit cave DURING training. brain feel rounding rock before final squish. this not normal quant. this QAT recovery rock, made for Q4 people. recipe (same as grug-9b-qat, scaled): full-weight QAT on grug-27b, fake int4 asymmetric group-32 with straight-through gradient, ~3M token of grug-think data, Adafactor LR 2e-6, 249 step on one H200. release = 25% QAT move + 75% original anchor (full QAT overcorrect, 9b teach grug this). then fresh BF16 export, quantize ONE time to Q4_K_M.

  • TinyLlama-1.1B-Chat-v1.0↗

    TinyLlama

    The TinyLlama project aims to **pretrain** a **1.1B Llama model on 3 trillion tokens**. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01. We adopted exactly the same architecture and tokenizer as Llama 2. This means TinyLlama can be plugged and played in many open-source projects built upon Llama. Besides, TinyLlama is compact with only 1.1B parameters. This compactness allows it to cater to a multitude of applications demanding a restricted computation and memory footprint. This is the chat model finetuned on top of TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T. **We follow HF's Zephyr's training recipe.** The model was " initially fine-tuned on a variant of the `UltraChat` dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT. We then further aligned the model with 🤗 TRL's `DPOTrainer` on the openbmb/UltraFeedback dataset, which contain 64k prompts and model completions that are ranked by GPT-4."

  • sam2.1-hiera-base-plus↗

    facebook

    Repository for SAM 2: Segment Anything in Images and Videos, a foundation model towards solving promptable visual segmentation in images and videos from FAIR. See the SAM 2 paper for more information. The official code is publicly release in this repo. Refer to the demo notebooks for details.